Xuejun/port cache model api (#15637)
* Add new compile model api to support hash model memory (#14543)
* Add new compile_model api for ONNX RUNTIME OV EP
Allow compile_model() accept model/weight data.
* Update minor place
* Cache model if possible
* Compute hash based on model_xml and model_weight
* Update typo
* Change hash key computation for model's weights
* Resolve test case issue
* Use tensor replace blob for hash computation
* Fix hash computation isssue and add more test cases
* Fix a build issue caused by data format
* Add ov::loaded_from_cache checking for CompileModelLoadFromMemoryTest (#15030)
* Add ov::loaded_from_cache checking for CompileModelLoadFromMemoryTestBase
* Skip gna in skip_tests_config
* Ignore empty tensor for hash calculation (#15282)
* Ignore empty tensor for hash calculation
* Added test
* Fix conflict
* Trigger ci run test for customer_A branch
---------
Co-authored-by: River Li <river.li@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
